相关论文: An Acceleration Scheme to The Local Directional Pa…

We propose Local Momentum Tracking (LMT), a novel distributed stochastic gradient method for solving distributed optimization problems over networks. To reduce communication overhead, LMT enables each agent to perform multiple local updates…

Traditional 3D Convolutional Neural Networks (CNNs) are computationally expensive, memory intensive, prone to overfit, and most importantly, there is a need to improve their feature learning capabilities. To address these issues, we propose…

Generating overtaking trajectories in autonomous racing is a challenging task, as the trajectory must satisfy the vehicle's dynamics and ensure safety and real-time performance running on resource-constrained hardware. This work proposes…

We define a SDP framework based on the RLSTD algorithm and multivariate simplex B-splines. We introduce a local forget factor capable of preserving the continuity of the simplex splines. This local forget factor is integrated with the RLSTD…

To deal with the complexity of the new bigger and more complex generation of data, machine learning (ML) techniques are probably the first and foremost used. For ML algorithms to produce results in a reasonable amount of time, they need to…

In this work, we address the motion planning problem for autonomous vehicles through a new lattice planning approach, called Feedback Enhanced Lattice Planner (FELP). Existing lattice planners have two major limitations, namely the high…

In this paper, a sampling-based trajectory planning algorithm for a laboratory-scale 3D gantry crane in an environment with static obstacles and subject to bounds on the velocity and acceleration of the gantry crane system is presented. The…

Top-$k$ frequent items detection is a fundamental task in data stream mining. Many promising solutions are proposed to improve memory efficiency while still maintaining high accuracy for detecting the Top-$k$ items. Despite the memory…

One of the most computationally challenging problems expected for the High-Luminosity Large Hadron Collider (HL-LHC) is determining the trajectory of charged particles during event reconstruction. Algorithms used at the LHC today rely on…

While texture analysis is largely addressed for images, the comparison of the geometric reliefs on surfaces embedded in the 3D space is still an open challenge. Starting from the Local Binary Pattern (LBP) description originally defined for…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

As minimum feature size and pitch spacing further decrease, triple patterning lithography (TPL) is a possible 193nm extension along the paradigm of double patterning lithography (DPL). However, there is very little study on TPL layout…

In large-scale traffic optimization, models based on Macroscopic Fundamental Diagram (MFD) are recognized for their efficiency in broad network analyses. However, they fail to reflect variations in the individual traffic status of each road…

Even though high-level synthesis (HLS) tools mitigate the challenges of programming domain-specific accelerators (DSAs) by raising the abstraction level, optimizing hardware directive parameters remains a significant hurdle. Existing…

This paper presents a modeling and optimization framework to compute the minimum-lap-time spatial trajectory and powertrain operation of racing cars in a computationally efficient fashion. Specifically, we first derive a quasi-steady-state…

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for…

In this paper, we present a new approach for improving 3D point and line mapping regression for camera re-localization. Previous methods typically rely on feature matching (FM) with stored descriptors or use a single network to encode both…

Conditional gradients constitute a class of projection-free first-order algorithms for smooth convex optimization. As such, they are frequently used in solving smooth convex optimization problems over polytopes, for which the computational…

The growth of large language models (LLMs) increases challenges of accelerating distributed training across multiple GPUs in different data centers. Moreover, concerns about data privacy and data exhaustion have heightened interest in…

The near-field (P2P) operator in the Multilevel Fast Multipole Algorithm (MLFMA) is a performance bottleneck on GPUs due to poor memory locality. This work introduces data redundancy to improve spatial locality by reducing memory access…